Earl St Sauver ad9c69860e Fix Cerebras context window errors not recognized (#17587) ... Add detection for Cerebras's context window exceeded error format: "Current length is X while limit is Y" This ensures LiteLLM raises ContextWindowExceededError instead of generic BadRequestError when Cerebras API calls exceed the model's context limit, enabling downstream libraries like DSPy to properly catch and handle these errors for automatic context management.		2025-12-08 19:02:06 -08:00
..
a2a_protocol	fix mypy linting	2025-12-03 19:43:29 -08:00
anthropic_interface
assistants
batch_completion
batches	fix: resolve ruff lint errors (#17490)	2025-12-04 14:12:57 -08:00
caching
completion_extras	fix(responses): prevent streaming tool_calls from being dropped when text + tool_calls (#17652)	2025-12-08 18:51:59 -08:00
containers
endpoints/speech/speech_to_completion_bridge
experimental_mcp_client
files	Add support for file content download for bedrock batches	2025-12-04 13:27:53 +05:30
fine_tuning
google_genai
images	[Refactor#2] litellm/init – Lazy-load utils to reduce memory + import time (#17171)	2025-12-03 11:40:16 -08:00
integrations	Native Webhook Integration Sumologic (#17630)	2025-12-07 23:23:39 -08:00
litellm_core_utils	Fix Cerebras context window errors not recognized (#17587)	2025-12-08 19:02:06 -08:00
llms	fix(openai): include 'user' param for responses API models (#17648)	2025-12-08 18:52:47 -08:00
ocr
passthrough	fix bedrock passthrough auth issue (#16879)	2025-11-24 18:44:59 -08:00
proxy	fix Azure AI Anthropic api-key header and passthrough cost calculation (#17656)	2025-12-08 18:50:26 -08:00
rag	[Feat] RAG API - QA - allow internal user keys to access api, allow using litellm credentials with API, raise clear exception when RAG API fails (#17169)	2025-11-26 17:07:30 -08:00
realtime_api	fix: tested e2e implementation and added sample config.	2025-11-26 12:37:13 +00:00
rerank_api	Add fireworks rerank support	2025-12-08 20:29:50 +05:30
responses	Add usage details in responses usage object	2025-12-08 11:51:47 +05:30
router_strategy
router_utils	fix(router): handle tools=None in filter_web_search_deployments (#17684)	2025-12-08 18:36:46 -08:00
search
secret_managers	fix: cyberark allow setting ssl verfiy to false (#17433)	2025-12-03 18:54:31 -08:00
skills	[Feat] New API - Claude Skills API (Anthropic) (#17042)	2025-11-24 15:01:40 -08:00
types	mitigate PydanticDeprecatedSince20 warnings (#17657)	2025-12-08 18:48:42 -08:00
vector_store_files
vector_stores	Fix vector store configuration synchronization failure	2025-12-05 11:46:14 +05:30
videos
__init__.py	[Feat] New model - add nvidia nim llama-3.2-nv-rerankqa-1b-v2 (#17670)	2025-12-08 15:25:23 -08:00
_lazy_imports.py	[Refactor#2] litellm/init – Lazy-load utils to reduce memory + import time (#17171)	2025-12-03 11:40:16 -08:00
_logging.py
_redis.py
_service_logger.py
_uuid.py
_version.py
budget_manager.py
constants.py	[Feat] New model - add bedrock writer models (#17685)	2025-12-08 17:49:06 -08:00
cost_calculator.py	Feat/mcp preserve tool metadata calltoolresult (#17561)	2025-12-05 16:15:22 -08:00
cost.json
exceptions.py
main.py	[New provider] Sap gen ai hub (#16053)	2025-12-08 12:31:06 -08:00
model_prices_and_context_window_backup.json	[Feat] New model - add bedrock writer models (#17685)	2025-12-08 17:49:06 -08:00
mypy.ini
py.typed
router.py	🆕 feat: support routing to only websearch supported deployments (#17500)	2025-12-04 14:18:20 -08:00
scheduler.py
timeout.py
utils.py	fix Azure AI Anthropic api-key header and passthrough cost calculation (#17656)	2025-12-08 18:50:26 -08:00